Follow
AYMEN AL-MARJANI
AYMEN AL-MARJANI
Verified email at amazon.com
Title
Cited by
Cited by
Year
Adaptive Sampling for Best Policy Identification in Markov Decision Processes
AA Marjani, A Proutiere
International Conference on Machine Learning, 7459-7468, 2021
28*2021
Navigating to the best policy in markov decision processes
A Al Marjani, A Garivier, A Proutiere
Advances in Neural Information Processing Systems 34, 25852-25864, 2021
212021
Near instance-optimal pac reinforcement learning for deterministic mdps
A Tirinzoni, A Al Marjani, E Kaufmann
Advances in neural information processing systems 35, 8785-8798, 2022
152022
Optimistic pac reinforcement learning: the instance-dependent view
A Tirinzoni, A Al-Marjani, E Kaufmann
International Conference on Algorithmic Learning Theory, 1460-1480, 2023
82023
Active coverage for pac reinforcement learning
A Al-Marjani, A Tirinzoni, E Kaufmann
The Thirty Sixth Annual Conference on Learning Theory, 5044-5109, 2023
72023
On the Complexity of All -Best Arms Identification
A Al Marjani, T Kocak, A Garivier
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2022
32022
On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence
A Azize, M Jourdan, A Al Marjani, D Basu
Advances in Neural Information Processing Systems 36, 2024
12024
Towards Instance-Optimality in Online PAC Reinforcement Learning
A Al-Marjani, A Tirinzoni, E Kaufmann
arXiv preprint arXiv:2311.05638, 2023
12023
Differentially Private Best-Arm Identification
A Azize, M Jourdan, AA Marjani, D Basu
arXiv preprint arXiv:2406.06408, 2024
2024
Adaptive Pure Exploration in Markov Decision Processes and Bandits
A Al Marjani
Ecole normale supérieure de lyon-ENS LYON, 2023
2023
Echantillonnage adaptatif pour l’identification de la politique optimale dans les PDMs
A Al Marjani, A Proutiere, P de Décision Markoviens, M Génératif
2021
On the complexity of All∈-Best Arms Identification
A Al Marjani, T Kocak, A Garivier
The system can't perform the operation now. Try again later.
Articles 1–12